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
     Beef
    -0.07
        	
↵
    -0.07
     nib
    -0.07
     dohod
    -0.07
     Link
    -0.06
     playoffs
    -0.06
     حف
    -0.06
    PB
    -0.06
     coeff
    -0.06
     Provid
    -0.06
    POSITIVE LOGITS
     mental
    0.14
     Mental
    0.12
     mentally
    0.11
     mentality
    0.09
     Ment
    0.09
     verbally
    0.08
    mental
    0.08
     ment
    0.08
     pulse
    0.07
     Moral
    0.07
    Act Density 0.008%

    No Known Activations