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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uggestion
    -0.06
    Observ
    -0.06
    /send
    -0.06
     пласти
    -0.06
     eq
    -0.06
    -Speed
    -0.06
     Twin
    -0.06
     Ward
    -0.06
    Escape
    -0.06
    Deg
    -0.06
    POSITIVE LOGITS
     sehen
    0.07
    WindowTitle
    0.07
     záv
    0.07
    сті
    0.06
     bian
    0.06
    .Maximum
    0.06
     homeowners
    0.06
    �다
    0.06
     altro
    0.06
    '][$
    0.06
    Act Density 0.022%

    No Known Activations