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

    Neuronpedia

    INDEX
    Explanations

    Computer mice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Finish
    -0.07
    eo
    -0.06
    Group
    -0.06
     statements
    -0.06
    吃
    -0.06
     bleiben
    -0.06
    Picture
    -0.06
    频
    -0.06
    .'''↵
    -0.06
    Expl
    -0.06
    POSITIVE LOGITS
    [].
    0.07
     Dynamo
    0.07
    �
    0.07
     Pett
    0.06
     lt
    0.06
    .codes
    0.06
     erotische
    0.06
    "]);
    0.06
    +lsi
    0.06
     }),
    0.06
    Act Density 0.006%

    No Known Activations