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

    Neuronpedia

    INDEX
    Explanations

    cat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dword
    -0.07
     Stanley
    -0.06
    .unit
    -0.06
     سازی
    -0.06
     Damon
    -0.06
     кому
    -0.06
    .ImageAlign
    -0.06
    _RETURNTRANSFER
    -0.06
     adam
    -0.06
     Eine
    -0.06
    POSITIVE LOGITS
     Living
    0.07
    KF
    0.06
     IMS
    0.06
    .ticket
    0.06
    pix
    0.06
     CCT
    0.06
     Vic
    0.06
    (no
    0.06
     вищ
    0.06
     CBS
    0.06
    Act Density 0.019%

    No Known Activations