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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .next
    -0.06
     Rig
    -0.06
    .flip
    -0.06
    >C
    -0.06
    毎
    -0.06
    	panic
    -0.06
     kinky
    -0.06
    (round
    -0.06
     DbContext
    -0.06
    .str
    -0.06
    POSITIVE LOGITS
    .
↵↵
    0.07
    apanese
    0.07
     attractive
    0.06
    ,[
    0.06
    invitation
    0.06
    lz
    0.06
     Бор
    0.06
    ubi
    0.06
    대표
    0.06
     missile
    0.06
    Act Density 0.046%

    No Known Activations