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

    Neuronpedia

    INDEX
    Explanations

    your

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dotyczą
    -0.08
    ♿
    -0.08
     أهم
    -0.07
     стала
    -0.07
    🥦
    -0.07
    uttgart
    -0.07
    นอกจาก
    -0.07
    귤
    -0.06
    егист
    -0.06
     CancellationToken
    -0.06
    POSITIVE LOGITS
    设想
    0.07
     TER
    0.07
     displayed
    0.07
    LD
    0.07
     mobs
    0.06
     MES
    0.06
     Older
    0.06
    _FIRE
    0.06
     PARTY
    0.06
    bx
    0.06
    Act Density 0.001%

    No Known Activations