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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    annes
    -0.07
     /////
    -0.06
    _unlock
    -0.06
    tal
    -0.06
     čtvrt
    -0.06
    abb
    -0.06
     joueur
    -0.06
    א
    -0.06
    spawn
    -0.06
    ifer
    -0.06
    POSITIVE LOGITS
     Doğu
    0.07
     сахар
    0.07
    .credit
    0.07
    _DER
    0.07
    fieldName
    0.07
     Metro
    0.07
     громадян
    0.06
    decor
    0.06
    เทศ
    0.06
     обрат
    0.06
    Act Density 0.008%

    No Known Activations