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

    Neuronpedia

    INDEX
    Explanations

    made

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .tax
    -0.08
    ñ
    -0.07
    bind
    -0.07
    amilies
    -0.07
    的经典
    -0.07
     HASH
    -0.07
    INE
    -0.07
    bill
    -0.07
    .pick
    -0.07
    ynth
    -0.07
    POSITIVE LOGITS
     And
    0.08
    蟆
    0.07
     autres
    0.07
    Void
    0.07
    |
↵
    0.07
     holders
    0.07
    🔓
    0.07
     housing
    0.07
    (*)(
    0.06
     loser
    0.06
    Act Density 0.014%

    No Known Activations