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

    Neuronpedia

    INDEX
    Explanations

    modeling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     кур
    -0.07
    алася
    -0.07
    	C
    -0.07
    Query
    -0.07
    �
    -0.07
    房
    -0.06
     К
    -0.06
    .XtraGrid
    -0.06
     tribute
    -0.06
    `='$
    -0.06
    POSITIVE LOGITS
    歳
    0.06
    时代
    0.06
    .reg
    0.06
    洲
    0.06
    yna
    0.06
    :N
    0.06
    ğine
    0.06
     courteous
    0.06
    所属
    0.06
    -empty
    0.06
    Act Density 0.324%

    No Known Activations