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

    Neuronpedia

    INDEX
    Explanations

    footnotes and citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gesicht
    -0.08
     sturdy
    -0.08
    -0.07
    -trash
    -0.07
     Aura
    -0.07
     kwem
    -0.07
     వై
    -0.07
     fear
    -0.07
    -solving
    -0.07
    elyn
    -0.07
    POSITIVE LOGITS
     foot
    0.16
    Foot
    0.12
     annotations
    0.12
     Foot
    0.12
     opmerkingen
    0.11
     Fuß
    0.11
     Annotation
    0.11
    _annotations
    0.11
     remarks
    0.10
     annotation
    0.10
    Act Density 0.017%

    No Known Activations