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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kullan
    -0.07
     telemetry
    -0.07
    Hola
    -0.07
    ุม
    -0.06
    classList
    -0.06
    Sadly
    -0.06
    导致
    -0.06
    ต
    -0.06
    HeaderCode
    -0.06
    işim
    -0.06
    POSITIVE LOGITS
     fears
    0.07
     Indoor
    0.07
     into
    0.06
    Frames
    0.06
    155
    0.06
     boy
    0.06
     rubbing
    0.06
    .linear
    0.06
     LM
    0.06
    NDAR
    0.06
    Act Density 0.021%

    No Known Activations