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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scaffold
    -0.07
    asured
    -0.06
    .es
    -0.06
    (bind
    -0.06
     změn
    -0.06
     RESPONS
    -0.06
     천
    -0.06
    !important
    -0.06
     restitution
    -0.06
     synonyms
    -0.06
    POSITIVE LOGITS
     inspect
    0.07
    #{@
    0.07
    िख
    0.06
    巻
    0.06
    سم
    0.06
    queued
    0.06
    ¶¶
    0.06
    	login
    0.06
    IFT
    0.06
    ельно
    0.06
    Act Density 0.005%

    No Known Activations