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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    662
    -0.08
     ऑफ
    -0.07
     ska
    -0.07
    _nat
    -0.07
    ancy
    -0.07
     tenga
    -0.07
    _formula
    -0.07
     fulfill
    -0.06
    он
    -0.06
     Gloves
    -0.06
    POSITIVE LOGITS
     JLabel
    0.06
    ../
    0.06
    ?</
    0.06
    ambre
    0.06
     nye
    0.06
    (padding
    0.06
    _neighbors
    0.06
     dare
    0.06
     ['/
    0.06
    owo
    0.06
    Act Density 0.035%

    No Known Activations