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

    Neuronpedia

    INDEX
    Explanations

    Hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AMB
    -0.08
    States
    -0.07
    atham
    -0.07
    тон
    -0.07
    בל
    -0.07
    wn
    -0.07
    Triangle
    -0.07
     urn
    -0.07
    _AMOUNT
    -0.07
     Maher
    -0.07
    POSITIVE LOGITS
    핬
    0.07
    سرط
    0.07
    驶
    0.07
     صغ
    0.07
    .Operation
    0.07
    	Mono
    0.06
     PHOTO
    0.06
    /errors
    0.06
    经开
    0.06
     rew
    0.06
    Act Density 0.004%

    No Known Activations