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

    Neuronpedia

    INDEX
    Explanations

    Dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _assert
    -0.07
     ﾍ
    -0.06
     fal
    -0.06
    _,
    -0.06
    (intent
    -0.06
    ility
    -0.06
    SPATH
    -0.06
    .Padding
    -0.06
    语
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    ');↵↵↵↵
    0.07
     inhab
    0.07
     setMessage
    0.07
     однов
    0.06
     disastrous
    0.06
    proper
    0.06
    Enh
    0.06
     デ
    0.06
     зни
    0.06
     screw
    0.06
    Act Density 0.040%

    No Known Activations