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

    Neuronpedia

    INDEX
    Explanations

    risk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     finding
    -0.28
     ANSI
    -0.27
     closed
    -0.26
     rise
    -0.26
     reaching
    -0.26
     closing
    -0.26
     NRA
    -0.25
     record
    -0.25
    utf
    -0.25
     pref
    -0.25
    POSITIVE LOGITS
    agoon
    0.29
    :num
    0.28
    addock
    0.27
    woods
    0.27
    odon
    0.27
    bia
    0.27
    æĪIJé¾Ļ
    0.26
     hè
    0.25
    isia
    0.25
    ddl
    0.25
    Act Density 0.011%

    No Known Activations