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

    Neuronpedia

    INDEX
    Explanations

    statement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	session
    -0.07
    	S
    -0.07
    地下
    -0.07
     convince
    -0.06
     loro
    -0.06
    .semantic
    -0.06
    대
    -0.06
    .invalid
    -0.06
     shareholders
    -0.06
     кан
    -0.06
    POSITIVE LOGITS
    _BATCH
    0.07
    aviors
    0.06
     GetName
    0.06
     tham
    0.06
    .provider
    0.06
    ff
    0.06
    small
    0.06
     {

↵
    0.06
     gamm
    0.06
    .assertIs
    0.06
    Act Density 0.014%

    No Known Activations