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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
     sliding
    -0.06
     withStyles
    -0.06
     bladder
    -0.06
    -load
    -0.06
    charges
    -0.06
    AX
    -0.06
    ฐาน
    -0.06
    ence
    -0.06
    token
    -0.06
    POSITIVE LOGITS
     cây
    0.07
     knockout
    0.07
     Secrets
    0.07
    '],['
    0.07
    強
    0.07
     εκ
    0.06
    uer
    0.06
    .cell
    0.06
    (phase
    0.06
     während
    0.06
    Act Density 0.014%

    No Known Activations