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

    Neuronpedia

    INDEX
    Explanations

    mentioned

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    firefox
    -0.07
    ního
    -0.07
    .recv
    -0.06
    .SYSTEM
    -0.06
     ostat
    -0.06
     Slayer
    -0.06
    .Layer
    -0.06
    .Private
    -0.06
    defaultValue
    -0.06
    crit
    -0.06
    POSITIVE LOGITS
    党
    0.07
    ريم
    0.07
     PvP
    0.06
    	register
    0.06
     �
    0.06
     establish
    0.06
     Dor
    0.06
    ged
    0.06
    okin
    0.06
     hương
    0.06
    Act Density 0.000%

    No Known Activations