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

    Neuronpedia

    INDEX
    Explanations

    descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     事
    -0.07
    ches
    -0.07
    SPELL
    -0.07
    Ав
    -0.07
    (TEST
    -0.06
    belie
    -0.06
    .Keyboard
    -0.06
    _CATEGORY
    -0.06
    실
    -0.06
     Πρό
    -0.06
    POSITIVE LOGITS
     useful
    0.06
     geldi
    0.06
    ỹ
    0.06
     sneak
    0.06
     retention
    0.06
    couldn
    0.06
    _dice
    0.06
     Theresa
    0.06
     overlap
    0.06
     untranslated
    0.06
    Act Density 0.060%

    No Known Activations