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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.09
    绿
    -0.08
     enger
    -0.08
     verdes
    -0.08
     Bone
    -0.07
     afirm
    -0.07
     velen
    -0.07
    .mult
    -0.07
    енні
    -0.07
     Multiplayer
    -0.07
    POSITIVE LOGITS
     ausprob
    0.08
     quay
    0.08
     extrema
    0.08
     boundaries
    0.08
     sead
    0.08
     endpoints
    0.08
    bereiche
    0.08
     mwisho
    0.08
     არსებული
    0.08
     পরীক্ষা
    0.08
    Act Density 0.035%
    No Known Activations