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

    Neuronpedia

    INDEX
    Explanations

    need/want

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    우
    -0.06
    DIC
    -0.06
    subset
    -0.06
    Child
    -0.06
    Microsoft
    -0.06
    _interrupt
    -0.06
    Hundreds
    -0.06
    Charlotte
    -0.06
    фектив
    -0.06
    Foot
    -0.06
    POSITIVE LOGITS
    oloj
    0.07
    ........................
    0.07
    ................................
    0.07
     levels
    0.06
    ää
    0.06
                
    0.06
     ************************
    0.06
    Details
    0.06
     İ
    0.06
     Details
    0.06
    Act Density 0.020%

    No Known Activations