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

    Neuronpedia

    INDEX
    Explanations

    Cloud computing responses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shoulder
    -0.08
    eldorf
    -0.07
    cargo
    -0.07
    Texto
    -0.07
    _corpus
    -0.07
     bahçe
    -0.07
     pomięd
    -0.07
     Также
    -0.07
    情节
    -0.07
    Message
    -0.07
    POSITIVE LOGITS
    cluster
    0.08
     alarms
    0.07
    _FUNCTION
    0.07
     Định
    0.07
    iloc
    0.07
     guessed
    0.07
    サー�
    0.06
    أفل
    0.06
    斫
    0.06
    Looking
    0.06
    Act Density 0.001%

    No Known Activations