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

    Neuronpedia

    INDEX
    Explanations

    (s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     awakened
    -0.06
    _minus
    -0.06
     kisses
    -0.06
    tt
    -0.06
     вог
    -0.06
     sung
    -0.06
     igual
    -0.06
     exerc
    -0.06
     understood
    -0.06
     ков
    -0.06
    POSITIVE LOGITS
    ни
    0.07
    _LOGIN
    0.07
     HinderedRotor
    0.07
    ([&
    0.07
    bound
    0.06
    (""));↵
    0.06
    \Json
    0.06
    art
    0.06
    <Member
    0.06
    )\<
    0.06
    Act Density 0.002%

    No Known Activations