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

    Neuronpedia

    INDEX
    Explanations

    Technical documentation/writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ä»ĬçĶŁ
    -0.31
    ãĤĤãĤĬ
    -0.28
    owler
    -0.26
    èįł
    -0.25
    天åłĤ
    -0.25
    ÑģÑĤÑĥп
    -0.25
    ambi
    -0.24
    å§Ĩ
    -0.23
    æļĦ
    -0.23
    åIJ²
    -0.23
    POSITIVE LOGITS
    æł·
    0.27
    metrics
    0.26
    bez
    0.25
    tbody
    0.24
    t
    0.24
    TypeInfo
    0.24
     taxed
    0.24
    getLocation
    0.24
    èĽĭ
    0.24
    ypress
    0.23
    Act Density 0.001%

    No Known Activations