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

    Neuronpedia

    INDEX
    Explanations

    mysterious events

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alternative
    0.51
     Alternative
    0.50
    alternative
    0.50
     finding
    0.46
     alternativa
    0.46
    Alternative
    0.45
     Finding
    0.45
    Finding
    0.42
    finding
    0.39
     study
    0.39
    POSITIVE LOGITS
    Development
    0.60
    development
    0.53
     development
    0.50
     Development
    0.49
     event
    0.47
     DEVELOPMENT
    0.45
    发展
    0.43
    ితి
    0.42
     disease
    0.40
     заболе
    0.40
    Act Density 0.005%

    No Known Activations