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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Olsen
    -0.07
     佐
    -0.06
     tung
    -0.06
     แก
    -0.06
    ForRow
    -0.06
    ibe
    -0.06
    .startActivity
    -0.06
     Feed
    -0.06
     万円
    -0.06
     Prairie
    -0.06
    POSITIVE LOGITS
    سل
    0.08
    ampaign
    0.07
     و
    0.07
    ีว
    0.07
    _TEMPLATE
    0.06
    .).↵↵
    0.06
    >{
    0.06
     depths
    0.06
    _dw
    0.06
     shots
    0.06
    Act Density 0.037%

    No Known Activations