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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     듣
    -0.08
    acad
    -0.07
     Path
    -0.07
    增加
    -0.07
    Bat
    -0.06
     Gregory
    -0.06
     Buenos
    -0.06
    -word
    -0.06
     assum
    -0.06
    Mount
    -0.06
    POSITIVE LOGITS
    -shopping
    0.07
    ccb
    0.07
    ,false
    0.06
    alers
    0.06
    /fontawesome
    0.06
     mehr
    0.06
     charismatic
    0.06
    .labels
    0.06
     Swansea
    0.06
    hour
    0.06
    Act Density 0.004%

    No Known Activations