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

    Neuronpedia

    INDEX
    Explanations

    Code-like words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    適用
    -0.07
    ainty
    -0.06
    งหมด
    -0.06
     Blackburn
    -0.06
    анные
    -0.06
    анием
    -0.06
    criminal
    -0.06
     Glover
    -0.06
    AccessType
    -0.06
    ками
    -0.06
    POSITIVE LOGITS
     yat
    0.07
     đậu
    0.07
    _SOUND
    0.07
    )r
    0.07
    _Product
    0.07
    ّم
    0.06
    _mirror
    0.06
     söyledi
    0.06
    _TCP
    0.06
    ...");↵↵
    0.06
    Act Density 0.011%

    No Known Activations