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

    Neuronpedia

    INDEX
    Explanations

    G

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FSIZE
    -0.07
    status
    -0.06
    nier
    -0.06
     Пет
    -0.06
    .Get
    -0.06
     Minist
    -0.06
    .steps
    -0.06
    	unset
    -0.06
     versch
    -0.06
    řit
    -0.06
    POSITIVE LOGITS
    Penn
    0.07
     라이
    0.07
     joint
    0.07
     renting
    0.07
     eigenen
    0.06
     Egg
    0.06
     Rebel
    0.06
    خی
    0.06
    >:
    0.06
     starts
    0.06
    Act Density 0.000%

    No Known Activations