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

    Neuronpedia

    INDEX
    Explanations

    mathematical/scientific statements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PIO
    -0.07
    ":"",↵
    -0.07
     primary
    -0.06
     luxury
    -0.06
    401
    -0.06
    //*
    -0.06
     sector
    -0.06
    격
    -0.06
    *",
    -0.06
    ráž
    -0.06
    POSITIVE LOGITS
     facile
    0.06
     pos
    0.06
    earable
    0.06
    cele
    0.06
     Trojan
    0.06
    Assigned
    0.06
     agregar
    0.06
     detailing
    0.06
     av
    0.06
    Classification
    0.06
    Act Density 0.026%

    No Known Activations