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

    Neuronpedia

    INDEX
    Explanations

    165

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mirror
    -0.09
    жу
    -0.08
     Sponsored
    -0.08
     Sponsor
    -0.08
    Sponsor
    -0.08
     Deco
    -0.08
    .MONTH
    -0.08
     invitations
    -0.08
     Pitch
    -0.08
     Invitations
    -0.08
    POSITIVE LOGITS
     기준
    0.10
     crossing
    0.09
    停止
    0.08
     advogado
    0.08
    达到
    0.08
     forensic
    0.08
     혈
    0.08
     compliance
    0.08
     criteria
    0.08
     cumplimiento
    0.08
    Act Density 0.004%

    No Known Activations