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

    Neuronpedia

    INDEX
    Explanations

    material

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Args
    -0.07
     Cooler
    -0.07
    _hours
    -0.07
     Burger
    -0.06
    .bucket
    -0.06
    ปลอดภ
    -0.06
     spou
    -0.06
    .skin
    -0.06
    .?
    -0.06
    RICS
    -0.06
    POSITIVE LOGITS
    تغ
    0.07
    feature
    0.06
     slime
    0.06
    smooth
    0.06
     tượng
    0.06
     Flesh
    0.06
     cognition
    0.06
     img
    0.06
     Final
    0.06
    lessness
    0.06
    Act Density 0.000%

    No Known Activations