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

    Neuronpedia

    INDEX
    Explanations

    say the ending -g

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    manifest
    -0.07
    토
    -0.06
     PDT
    -0.06
     Twice
    -0.06
     TERMIN
    -0.06
     Nylon
    -0.06
    LANGUAGE
    -0.06
     MOVE
    -0.06
     crates
    -0.06
     specialized
    -0.06
    POSITIVE LOGITS
    iculture
    0.06
    ulfilled
    0.06
    "=>$
    0.06
    _UD
    0.06
    ladım
    0.06
    صة
    0.06
    (cond
    0.06
     культур
    0.06
    μερα
    0.06
    -picker
    0.05
    Act Density 0.003%

    No Known Activations