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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chief
    -0.07
     compagn
    -0.07
     accr
    -0.07
     Saul
    -0.06
     Dropout
    -0.06
     �
    -0.06
    oval
    -0.06
     implying
    -0.06
     factions
    -0.06
    評
    -0.06
    POSITIVE LOGITS
    ریه
    0.06
    兽
    0.06
    arms
    0.06
    ंट
    0.06
    Exercise
    0.06
    _Resource
    0.06
    /class
    0.06
    -established
    0.06
    explo
    0.06
    getUser
    0.06
    Act Density 0.029%

    No Known Activations