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

    Neuronpedia

    INDEX
    Explanations

    secrets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     acquire
    -0.07
     dört
    -0.07
    ocz
    -0.06
     Argument
    -0.06
     miscon
    -0.06
     Romantic
    -0.06
     personne
    -0.06
    adratic
    -0.06
    暴
    -0.06
    .IsFalse
    -0.06
    POSITIVE LOGITS
    _PS
    0.06
    .ns
    0.06
    ssl
    0.06
     nit
    0.06
    213
    0.06
    ώντας
    0.06
     sunscreen
    0.06
     AIR
    0.06
    _WS
    0.06
    loe
    0.06
    Act Density 0.026%

    No Known Activations