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

    Neuronpedia

    INDEX
    Explanations

    graft

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hot
    -0.06
    073
    -0.06
     proprietary
    -0.06
     Terror
    -0.06
     N
    -0.06
     kitchens
    -0.06
    _comment
    -0.06
    .RESULT
    -0.06
     Anchor
    -0.06
     Building
    -0.06
    POSITIVE LOGITS
    @Id
    0.07
    十一
    0.07
     Αγ
    0.06
     pretended
    0.06
    {id
    0.06
    اذا
    0.06
     enthusi
    0.06
    �
    0.06
    iasi
    0.06
     наруш
    0.06
    Act Density 0.004%

    No Known Activations