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

    Neuronpedia

    INDEX
    Explanations

    its

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     triangle
    -0.08
    right
    -0.07
    _at
    -0.07
    _Right
    -0.07
     Mas
    -0.06
    Appearance
    -0.06
     mah
    -0.06
    ><!--
    -0.06
    RouterModule
    -0.06
    Lat
    -0.06
    POSITIVE LOGITS
     Condition
    0.06
    許
    0.06
     uplift
    0.06
     SIMD
    0.06
     Pluto
    0.06
     thể
    0.06
    PullParser
    0.06
     "..
    0.06
     climbers
    0.06
    APSHOT
    0.06
    Act Density 0.005%

    No Known Activations