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

    Neuronpedia

    INDEX
    Explanations

    plant extracts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    、《
    -0.07
     kvinnor
    -0.07
     Jal
    -0.07
     Famil
    -0.07
     naked
    -0.06
    ็นพ
    -0.06
    �
    -0.06
     Smartphone
    -0.06
     дитини
    -0.06
     nord
    -0.06
    POSITIVE LOGITS
     usual
    0.06
    eral
    0.06
    216
    0.06
     oč
    0.06
    .tile
    0.06
    sys
    0.06
    -wsj
    0.06
    .secret
    0.06
     profession
    0.06
     facts
    0.06
    Act Density 0.000%

    No Known Activations