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

    Neuronpedia

    INDEX
    Explanations

    phrases related to claims and evidence

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

    claims to have discovered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    visuel
    -0.46
    Diweddarwch
    -0.45
     burbujas
    -0.45
     sonriendo
    -0.44
     liderança
    -0.43
     nationaux
    -0.43
     calcetines
    -0.42
     cejas
    -0.41
     besos
    -0.41
     knji
    -0.40
    POSITIVE LOGITS
    EndInit
    0.50
    oneofs
    0.49
     AssemblyTitle
    0.49
    ukone
    0.48
    endpush
    0.47
    UseVisualStyle
    0.47
     Perman
    0.46
    Perman
    0.46
    artifactId
    0.45
    Libert
    0.44
    Act Density 0.073%

    No Known Activations