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

    Neuronpedia

    INDEX
    Explanations

    Can

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thighs
    -0.06
    stu
    -0.06
    Germany
    -0.06
    	word
    -0.06
    updated
    -0.06
     Romania
    -0.06
     enduring
    -0.06
     ttl
    -0.06
     तरह
    -0.06
     thumb
    -0.06
    POSITIVE LOGITS
     karak
    0.08
    άν
    0.07
    anlık
    0.07
     Coalition
    0.07
    CursorPosition
    0.07
    pee
    0.06
     pesso
    0.06
     kurs
    0.06
    ьер
    0.06
     Wellness
    0.06
    Act Density 0.014%

    No Known Activations