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

    Neuronpedia

    INDEX
    Explanations

    -type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ursion
    -0.07
    EK
    -0.07
    EEK
    -0.07
    INATION
    -0.07
     Array
    -0.07
     twentieth
    -0.07
     '',
    -0.07
    Serialize
    -0.06
    iw
    -0.06
    ellung
    -0.06
    POSITIVE LOGITS
    latex
    0.07
    Loaded
    0.07
     LeBron
    0.07
    fit
    0.06
    laws
    0.06
    	save
    0.06
    兼容
    0.06
    的一切
    0.06
    -fire
    0.06
    _locked
    0.06
    Act Density 0.002%

    No Known Activations