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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sonian
    -0.07
    стин
    -0.06
    皇
    -0.06
    arsity
    -0.06
     aliases
    -0.06
     Checkbox
    -0.06
     computed
    -0.06
     etiquette
    -0.06
    get
    -0.06
    oloji
    -0.06
    POSITIVE LOGITS
    osc
    0.07
    Assignable
    0.07
    Ca
    0.06
    (TEXT
    0.06
    _flux
    0.06
    dress
    0.06
    FIG
    0.06
    sizlik
    0.06
     poco
    0.06
    inside
    0.06
    Act Density 0.144%

    No Known Activations