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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     policemen
    -0.08
     regulatory
    -0.07
     dynamic
    -0.07
    قیق
    -0.07
    hes
    -0.07
     inject
    -0.07
     hosts
    -0.06
     Healthy
    -0.06
    -weight
    -0.06
     guarded
    -0.06
    POSITIVE LOGITS
     شوند
    0.07
    @endif
    0.07
    rcode
    0.06
    reff
    0.06
     istiyor
    0.06
    idepress
    0.06
    ıyorlar
    0.06
    드리
    0.06
     hissed
    0.06
    /lgpl
    0.06
    Act Density 0.031%

    No Known Activations