Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating differing beliefs or values among people or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    compatibility differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.56
     indígen
    -0.52
    chieht
    -0.51
    HasAnnotation
    -0.49
     pleaſure
    -0.49
     ſtate
    -0.48
    verifyException
    -0.48
     ſche
    -0.47
     desmotivaciones
    -0.47
     InputDecoration
    -0.47
    POSITIVE LOGITS
     AssemblyCulture
    0.45
    IntoConstraints
    0.39
     Bond
    0.39
    ThroughAttribute
    0.38
    VersionUID
    0.36
    弾
    0.36
     compatibility
    0.33
     incompatibility
    0.32
     EClass
    0.32
     الحره
    0.30
    Act Density 0.086%

    No Known Activations