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

    Neuronpedia

    INDEX
    Explanations

    diverse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     precip
    -0.07
     laat
    -0.07
    “Well
    -0.07
     rehab
    -0.06
     facilitating
    -0.06
     beef
    -0.06
    	open
    -0.06
    	HAL
    -0.06
    "Well
    -0.06
     Fuck
    -0.06
    POSITIVE LOGITS
     diverse
    0.08
    ます
    0.08
    MIC
    0.07
     lille
    0.07
     تر
    0.07
    dre
    0.06
    沃
    0.06
    소
    0.06
     e
    0.06
     تسم
    0.06
    Act Density 0.009%

    No Known Activations