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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tract
    -0.07
    挓
    -0.06
    inel
    -0.06
    ()
    -0.06
    enterprise
    -0.06
    (C
    -0.06
     tween
    -0.06
     addChild
    -0.06
     derive
    -0.06
    trzymał
    -0.06
    POSITIVE LOGITS
    旴
    0.08
    sb
    0.07
    regon
    0.07
    führ
    0.07
    outed
    0.07
     headings
    0.07
     consideration
    0.07
    LETTE
    0.07
    -Day
    0.07
    /rem
    0.07
    Act Density 0.000%

    No Known Activations