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

    Neuronpedia

    INDEX
    Explanations

    **

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Survival
    -0.06
    .mul
    -0.06
    	part
    -0.06
     출
    -0.05
    .get
    -0.05
    leness
    -0.05
    薄
    -0.05
    -k
    -0.05
    _corpus
    -0.05
    CTRL
    -0.05
    POSITIVE LOGITS
    pun
    0.07
     досяг
    0.07
    ００
    0.07
     Sending
    0.07
    ::::
    0.07
    iamond
    0.06
     addressed
    0.06
    (stage
    0.06
    caps
    0.06
     [↵
    0.06
    Act Density 0.003%

    No Known Activations