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

    Neuronpedia

    INDEX
    Explanations

    finite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /right
    -0.06
     crafts
    -0.06
     Clip
    -0.06
     cunning
    -0.06
     cruising
    -0.06
     случаев
    -0.06
     Stars
    -0.06
     drawers
    -0.06
     gratuito
    -0.06
     hiding
    -0.06
    POSITIVE LOGITS
     نه
    0.07
    .vote
    0.07
    ICI
    0.07
     περιο
    0.07
     �
    0.06
     expenditures
    0.06
     Ferd
    0.06
     Duchess
    0.06
     besten
    0.06
    enticate
    0.06
    Act Density 0.007%

    No Known Activations