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

    Neuronpedia

    INDEX
    Explanations

    providing support/resources

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Spaces
    -0.07
     preempt
    -0.07
    (insert
    -0.07
    Guy
    -0.06
     Reeves
    -0.06
     this
    -0.06
    inated
    -0.06
     Pussy
    -0.06
     Rename
    -0.06
    :NSUTF
    -0.06
    POSITIVE LOGITS
    _COD
    0.07
    ิบ
    0.07
    ('${
    0.06
     bite
    0.06
    _ISO
    0.06
     giàu
    0.06
    dataTable
    0.06
    �
    0.06
    .borrow
    0.06
     엄마
    0.06
    Act Density 0.039%

    No Known Activations