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

    Neuronpedia

    INDEX
    Explanations

    units like ohms, watts, amps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ï¼ı
    -0.10
    >NN
    -0.09
     eas
    -0.09
     поÑĤом
    -0.09
     Wagner
    -0.09
    Å¡ti
    -0.09
    ï¾Į
    -0.08
     acronym
    -0.08
     ï¼İ
    -0.08
    PFN
    -0.08
    POSITIVE LOGITS
     Forums
    0.09
    vang
    0.09
     McKin
    0.09
     proh
    0.09
    IFO
    0.08
     Dra
    0.08
    //=
    0.08
    znik
    0.08
    hlas
    0.08
     hob
    0.08
    Act Density 0.194%

    No Known Activations