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

    Neuronpedia

    INDEX
    Explanations

    apostrophe

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kurum
    -0.07
    国际
    -0.06
    View
    -0.06
    Project
    -0.06
    -routing
    -0.06
    anchise
    -0.06
     presented
    -0.06
     Torch
    -0.06
    	content
    -0.06
    ended
    -0.06
    POSITIVE LOGITS
     espa
    0.07
    ื้
    0.07
    Nib
    0.07
     PWM
    0.06
     influential
    0.06
    bbc
    0.06
     인기
    0.06
     ub
    0.06
    Debe
    0.06
     susceptible
    0.06
    Act Density 0.003%

    No Known Activations