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

    Neuronpedia

    INDEX
    Explanations

    business analysis and research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     t
    -0.07
     soak
    -0.07
     JT
    -0.07
     correct
    -0.07
     viewpoint
    -0.07
     palace
    -0.06
     impulse
    -0.06
     projecting
    -0.06
    EXP
    -0.06
    	q
    -0.06
    POSITIVE LOGITS
     trí
    0.07
    (square
    0.06
     bezpečnost
    0.06
    Unsupported
    0.06
    .setState
    0.06
    .methods
    0.06
     vývoj
    0.06
    _SAFE
    0.06
     Luật
    0.06
    CreateInfo
    0.06
    Act Density 0.044%

    No Known Activations