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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     —↵↵
    -0.28
    èī¯
    -0.28
    -↵↵
    -0.27
    å¡ĺ
    -0.26
    -,
    -0.26
     put
    -0.26
    çľŁäºº
    -0.25
    –↵↵
    -0.25
    edImage
    -0.24
    unning
    -0.24
    POSITIVE LOGITS
    rish
    0.27
    ecure
    0.25
    ocio
    0.25
    ÑĪиб
    0.25
    lush
    0.25
    çīĩåŃIJ
    0.24
    rapper
    0.24
    -fe
    0.23
     feasible
    0.23
    /colors
    0.23
    Act Density 1.146%

    No Known Activations