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

    Neuronpedia

    INDEX
    Explanations

    connection/separation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     σχ
    -0.07
    ervention
    -0.07
     tv
    -0.06
     rider
    -0.06
    τό
    -0.06
     conforme
    -0.06
    09
    -0.06
     للت
    -0.06
    .handleClick
    -0.06
     militant
    -0.06
    POSITIVE LOGITS
    zte
    0.07
    -\
    0.06
    .↵
    0.06
    умов
    0.06
    。
↵
    0.06
    hait
    0.06
    ,.
    0.06
    (;
    0.06
    álu
    0.06
    rada
    0.06
    Act Density 0.527%

    No Known Activations