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

    Neuronpedia

    INDEX
    Explanations

    jail

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Polygon
    -0.07
     brothers
    -0.07
    资产
    -0.07
    p
    -0.06
    para
    -0.06
     querying
    -0.06
    ीएस
    -0.06
     eldre
    -0.06
    compat
    -0.06
     empathy
    -0.06
    POSITIVE LOGITS
     jail
    0.16
     Jail
    0.15
     jails
    0.11
     jailed
    0.11
    ail
    0.09
     Bail
    0.07
    AIL
    0.07
     jit
    0.07
     hail
    0.07
    antanamo
    0.07
    Act Density 0.002%

    No Known Activations