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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     voks
    -0.07
    Answer
    -0.07
    ampus
    -0.06
    spo
    -0.06
    .READ
    -0.06
     распред
    -0.06
     Hex
    -0.06
     overcoming
    -0.06
     otom
    -0.06
     vå
    -0.06
    POSITIVE LOGITS
     яким
    0.07
    icot
    0.06
     thigh
    0.06
     oldukları
    0.06
     who
    0.06
     qui
    0.06
    ++;↵
    0.06
    다면
    0.06
    子
    0.06
    EHICLE
    0.06
    Act Density 0.015%

    No Known Activations