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

    Neuronpedia

    INDEX
    Explanations

    say "sea/salt" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    culture
    -0.07
    Miller
    -0.06
    Adventure
    -0.06
    icker
    -0.06
    AA
    -0.06
    lements
    -0.06
    DataFrame
    -0.06
    ura
    -0.06
    flat
    -0.06
    ラー
    -0.06
    POSITIVE LOGITS
    &P
    0.07
     snatch
    0.06
    })↵↵↵
    0.06
     chatte
    0.06
    \models
    0.06
    �
    0.06
    меж
    0.06
    \u
    0.06
    Subjects
    0.06
     diesel
    0.06
    Act Density 0.024%

    No Known Activations