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

    Neuronpedia

    INDEX
    Explanations

    Lists with numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bestimm
    -0.07
     степ
    -0.07
    `:
    -0.07
     پژوه
    -0.06
    (!_
    -0.06
     QUE
    -0.06
     (!
    -0.06
     annoying
    -0.06
     defending
    -0.06
    Ц
    -0.06
    POSITIVE LOGITS
     Emily
    0.07
     工
    0.07
     mediator
    0.06
     ย
    0.06
    _BOOT
    0.06
     Как
    0.06
    uite
    0.06
    extAlignment
    0.06
     din
    0.06
    ahas
    0.06
    Act Density 0.024%

    No Known Activations