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

    Neuronpedia

    INDEX
    Explanations

    will/be

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Casey
    -0.08
    /+
    -0.06
    .getPath
    -0.06
    -team
    -0.06
    뺘
    -0.06
    Crime
    -0.06
    成本
    -0.06
     flaw
    -0.06
     profesional
    -0.06
    _Zero
    -0.06
    POSITIVE LOGITS
    	done
    0.08
    Adds
    0.08
    👢
    0.07
     ../../
    0.07
    都會
    0.07
     transported
    0.06
        
    0.06
     acts
    0.06
    "↵↵
    0.06
    (num
    0.06
    Act Density 0.032%

    No Known Activations