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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	that
    -0.07
    ungeon
    -0.07
    ้าว
    -0.06
     frightened
    -0.06
    [Double
    -0.06
    ingle
    -0.06
    oubted
    -0.06
    ump
    -0.06
    Logging
    -0.06
     ----------------------------------------------------------------------------↵
    -0.06
    POSITIVE LOGITS
     гар
    0.07
     Werner
    0.07
     Resolve
    0.06
     charged
    0.06
    _COLUMN
    0.06
    Too
    0.06
     BA
    0.06
    clusion
    0.06
    出现
    0.06
     KEY
    0.06
    Act Density 0.342%

    No Known Activations