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

    Neuronpedia

    INDEX
    Explanations

    Vil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kot
    -0.07
    AGMENT
    -0.06
    oyo
    -0.06
    ітет
    -0.06
    971
    -0.06
    atha
    -0.06
     عليها
    -0.06
    usaha
    -0.06
     batteries
    -0.06
     joker
    -0.06
    POSITIVE LOGITS
     gated
    0.07
    (rng
    0.07
     �
    0.07
    _input
    0.07
     nearly
    0.07
    _signature
    0.07
     Essex
    0.07
     bfd
    0.06
    	cpu
    0.06
     narc
    0.06
    Act Density 0.000%

    No Known Activations