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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .out
    -0.07
     centrif
    -0.07
    quot
    -0.06
     Manitoba
    -0.06
     countert
    -0.06
     Scor
    -0.06
    amt
    -0.06
    rott
    -0.06
     srv
    -0.06
    icari
    -0.06
    POSITIVE LOGITS
     даже
    0.06
    Unnamed
    0.06
    一般
    0.06
     而
    0.06
     وم
    0.06
    ardless
    0.06
     pagar
    0.06
     //↵
    0.06
     asses
    0.06
     towing
    0.06
    Act Density 0.004%

    No Known Activations