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

    Neuronpedia

    INDEX
    Explanations

    post

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Enterprise
    -0.06
     generalized
    -0.06
     magnetic
    -0.06
     servings
    -0.06
     blend
    -0.06
     JOIN
    -0.06
     Slow
    -0.06
    (my
    -0.06
    Scores
    -0.06
     cheek
    -0.06
    POSITIVE LOGITS
    بار
    0.08
     charger
    0.07
     afterwards
    0.07
     Afterwards
    0.07
     строк
    0.07
    .getResponse
    0.06
    olumbia
    0.06
    ')}}</
    0.06
    JsonProperty
    0.06
    .clicked
    0.06
    Act Density 0.004%

    No Known Activations