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

    Neuronpedia

    INDEX
    Explanations

    journaling or journals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    1.80
    ح
    1.13
    ge
    1.13
    be
    1.06
    v
    1.06
    st
    1.05
    im
    1.04
    ts
    1.02
    س
    1.01
    f
    0.99
    POSITIVE LOGITS
     cohort
    0.98
    larının
    0.93
     seu
    0.92
    0.92
     n
    0.92
     snorkel
    0.92
    리
    0.92
     tris
    0.90
     राह
    0.89
     MHD
    0.88
    Act Density 0.002%

    No Known Activations