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

    Neuronpedia

    INDEX
    Explanations

    articles and punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    니까
    -0.08
     regexp
    -0.06
    /pm
    -0.06
    nonce
    -0.06
    ／:
    -0.06
    aro
    -0.06
     useClass
    -0.06
     courteous
    -0.06
    _security
    -0.06
    운드
    -0.06
    POSITIVE LOGITS
    anzi
    0.07
     Abram
    0.06
    becue
    0.06
    illusion
    0.06
     Gentle
    0.06
     af
    0.06
    _ATOM
    0.06
     ﻣ
    0.06
    (CH
    0.06
     dahi
    0.06
    Act Density 0.028%

    No Known Activations