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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _multip
    -0.07
     deflect
    -0.07
     Thickness
    -0.07
     HW
    -0.07
    .setEditable
    -0.06
    .lv
    -0.06
    .receiver
    -0.06
     Sü
    -0.06
     fø
    -0.06
    -duration
    -0.06
    POSITIVE LOGITS
     дол
    0.07
     Oasis
    0.07
     있을
    0.07
    ijd
    0.07
    tml
    0.06
    �
    0.06
    -hooks
    0.06
     Tarif
    0.06
    	config
    0.06
     geçen
    0.06
    Act Density 0.020%

    No Known Activations