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

    Neuronpedia

    INDEX
    Explanations

    objective

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clan
    -0.07
    Man
    -0.07
    _rw
    -0.06
     dn
    -0.06
    Can
    -0.06
    71
    -0.06
     spell
    -0.06
     area
    -0.06
    全
    -0.06
     pack
    -0.06
    POSITIVE LOGITS
     objective
    0.13
     objectives
    0.11
     Objective
    0.11
    objective
    0.09
    ovic
    0.09
    Objective
    0.08
    madı
    0.08
     medios
    0.08
     الد
    0.08
    Compute
    0.07
    Act Density 0.013%

    No Known Activations