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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Previously
    -0.06
     resistant
    -0.06
     ци
    -0.06
     suffice
    -0.06
    �
    -0.06
    CASCADE
    -0.06
     jury
    -0.06
    -HT
    -0.06
     ali
    -0.06
    _agents
    -0.06
    POSITIVE LOGITS
     getConnection
    0.08
    OLA
    0.07
     इत
    0.07
     instructed
    0.07
    (channel
    0.07
     Patron
    0.06
    pets
    0.06
    ع
    0.06
    check
    0.06
    Soon
    0.06
    Act Density 0.005%

    No Known Activations