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

    Neuronpedia

    INDEX
    Explanations

    Mental health

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deficiencies
    -0.07
    ocytes
    -0.06
    _o
    -0.06
     الاست
    -0.06
     hos
    -0.06
     díl
    -0.06
     Mandarin
    -0.06
     Taiwan
    -0.06
     عب
    -0.06
    FI
    -0.06
    POSITIVE LOGITS
    NR
    0.06
    "",
    0.06
    	
↵	
↵
    0.06
    ुछ
    0.06
    Optional
    0.06
     shoppers
    0.06
    jobs
    0.06
    Shadow
    0.06
    รอง
    0.06
    .Sequence
    0.05
    Act Density 0.010%

    No Known Activations