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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     своей
    -0.07
     �
    -0.06
    =message
    -0.06
    /basic
    -0.06
    bracht
    -0.06
     replay
    -0.06
    _RATE
    -0.06
     fungal
    -0.06
    ोफ
    -0.06
    owied
    -0.06
    POSITIVE LOGITS
     probs
    0.07
    _{
    0.07
     Lane
    0.07
    +(\
    0.06
     skating
    0.06
    ussels
    0.06
     perceptions
    0.06
    (ps
    0.06
    iners
    0.06
     한
    0.06
    Act Density 0.000%

    No Known Activations