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

    Neuronpedia

    INDEX
    Explanations

    units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NONINFRINGEMENT
    -0.07
    alion
    -0.07
     المغرب
    -0.06
     solicitud
    -0.06
     sanitized
    -0.06
    andaş
    -0.06
    หร
    -0.06
    ерин
    -0.06
     أن
    -0.06
    -leaning
    -0.06
    POSITIVE LOGITS
    Pub
    0.07
     Sequential
    0.07
    Doug
    0.06
    inals
    0.06
    <-
    0.06
     screen
    0.06
     clearance
    0.06
     цент
    0.06
    /=
    0.06
    /Object
    0.06
    Act Density 0.000%

    No Known Activations