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
    dfa
    -0.08
     capitalized
    -0.08
    Phrase
    -0.07
     popul
    -0.07
    _Parameter
    -0.07
     Ney
    -0.07
     cowboy
    -0.07
     Beta
    -0.07
     fatty
    -0.07
    暮
    -0.07
    POSITIVE LOGITS
     Each
    0.07
    _age
    0.07
    ：↵↵
    0.07
    (&
    0.07
    瞧
    0.06
     seeing
    0.06
    -focus
    0.06
    	texture
    0.06
    的部分
    0.06
    菇
    0.06
    Act Density 0.006%

    No Known Activations