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

    Neuronpedia

    INDEX
    Explanations

    100

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gettext
    -0.07
     sexuality
    -0.07
    .uniform
    -0.06
    ंधन
    -0.06
     Knife
    -0.06
     kötü
    -0.06
     poner
    -0.06
    Location
    -0.06
     mundane
    -0.06
    -letter
    -0.06
    POSITIVE LOGITS
    MAIL
    0.07
     앉
    0.07
     сила
    0.06
     dess
    0.06
     flyer
    0.06
    ует
    0.06
     concentrations
    0.06
    	curl
    0.06
    void
    0.06
     indign
    0.06
    Act Density 0.002%

    No Known Activations