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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Interview
    -0.06
    atisfaction
    -0.06
    姐
    -0.06
     지난
    -0.06
    時間
    -0.06
    _STARTED
    -0.06
    anian
    -0.06
    (env
    -0.06
     slash
    -0.06
    elijk
    -0.06
    POSITIVE LOGITS
     �
    0.07
    _Master
    0.07
    _traj
    0.07
    ~-~-~-~-
    0.06
    찬
    0.06
     घ
    0.06
    _SANITIZE
    0.06
    inta
    0.06
    .btnExit
    0.06
     nip
    0.06
    Act Density 0.004%

    No Known Activations