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

    Neuronpedia

    INDEX
    Explanations

    !=

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .JWT
    -0.07
    /event
    -0.07
     occup
    -0.07
     hazard
    -0.07
    soles
    -0.06
    瑂
    -0.06
     Silicone
    -0.06
    gings
    -0.06
     congen
    -0.06
    삵
    -0.06
    POSITIVE LOGITS
     clauses
    0.07
     conducted
    0.07
     restrained
    0.07
     DEL
    0.07
    Dec
    0.07
    	direction
    0.07
    veled
    0.07
    几
    0.07
    raised
    0.07
    部门
    0.06
    Act Density 0.001%

    No Known Activations