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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ふ
    -0.06
    .When
    -0.06
    When
    -0.06
    ०
    -0.06
     κρα
    -0.06
    -lg
    -0.06
    -0.06
    альна
    -0.06
    %"
    -0.05
    -small
    -0.05
    POSITIVE LOGITS
    allax
    0.07
     ERR
    0.07
     organism
    0.07
     Bened
    0.07
    ître
    0.07
     genome
    0.07
     exploit
    0.07
    スティ
    0.07
    itions
    0.07
    ubble
    0.06
    Act Density 0.039%

    No Known Activations