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

    Neuronpedia

    INDEX
    Explanations

    interference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Paypal
    -0.07
     Bor
    -0.07
    Checksum
    -0.06
     zal
    -0.06
    Accept
    -0.06
    banana
    -0.06
    (":/
    -0.06
     pneum
    -0.06
    _AX
    -0.06
    abyrin
    -0.06
    POSITIVE LOGITS
     jung
    0.07
    evento
    0.07
    ологіч
    0.06
     crafting
    0.06
     い
    0.06
     FRIEND
    0.06
    .rotation
    0.06
    Mill
    0.06
    .number
    0.06
     norms
    0.06
    Act Density 0.007%

    No Known Activations