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

    Neuronpedia

    INDEX
    Explanations

    check / checking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    מער
    -0.08
    来的
    -0.08
    .Manifest
    -0.07
    -0.07
    进
    -0.07
    р
    -0.07
     entrance
    -0.07
     shocked
    -0.07
     nö
    -0.07
    281
    -0.07
    POSITIVE LOGITS
    Checkbox
    0.12
    checkbox
    0.11
     checkbox
    0.11
     Checkbox
    0.10
    -checkbox
    0.10
     گزینه
    0.09
    .checkbox
    0.09
    _checkbox
    0.09
    .Checked
    0.09
    箱
    0.09
    Act Density 0.011%
    No Known Activations