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

    Neuronpedia

    INDEX
    Explanations

    educated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	exp
    -0.07
    cline
    -0.07
    計劃
    -0.06
    Five
    -0.06
    WHAT
    -0.06
    áfico
    -0.06
     blacklist
    -0.06
    まった
    -0.06
    orses
    -0.06
    UMP
    -0.05
    POSITIVE LOGITS
    (proc
    0.09
     ourselves
    0.07
    isel
    0.07
     Lana
    0.07
    (low
    0.06
     contamination
    0.06
    (dir
    0.06
     thoải
    0.06
    .loss
    0.06
    (request
    0.06
    Act Density 0.021%

    No Known Activations