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

    Neuronpedia

    INDEX
    Explanations

    Warnings and disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prostate
    -0.08
    _services
    -0.07
     popping
    -0.07
     explores
    -0.06
    Sun
    -0.06
     defends
    -0.06
     next
    -0.06
     potatoes
    -0.06
    arsing
    -0.06
    utdown
    -0.06
    POSITIVE LOGITS
    γή
    0.06
     Alexand
    0.06
    "<?
    0.06
    튜
    0.06
    _di
    0.06
     uncomment
    0.06
     خارجية
    0.06
     Behavioral
    0.06
    !↵↵↵↵
    0.05
    %'
    0.05
    Act Density 0.002%

    No Known Activations