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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scor
    -0.07
    	damage
    -0.07
    /user
    -0.06
    .breakpoints
    -0.06
     useHistory
    -0.06
    _version
    -0.06
     Rookie
    -0.06
     başkan
    -0.06
    _capabilities
    -0.06
     kurum
    -0.06
    POSITIVE LOGITS
    Invoice
    0.07
     many
    0.07
    lington
    0.07
     between
    0.06
    CSI
    0.06
     featured
    0.06
     monthly
    0.06
     someone
    0.06
    enu
    0.06
     Thunder
    0.06
    Act Density 0.000%

    No Known Activations