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

    Neuronpedia

    INDEX
    Explanations

    consumer products

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	score
    -0.07
     site
    -0.07
    intl
    -0.07
    γά
    -0.07
     potato
    -0.06
     Targets
    -0.06
     sour
    -0.06
     шк
    -0.06
     Mixer
    -0.06
    -process
    -0.06
    POSITIVE LOGITS
     �
    0.06
     theres
    0.06
    .POST
    0.06
    ницип
    0.06
     racially
    0.06
    態
    0.06
    ーバ
    0.06
     hoş
    0.06
     tabindex
    0.06
    oloj
    0.06
    Act Density 0.055%

    No Known Activations