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

    Neuronpedia

    INDEX
    Explanations

    arc and rc sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जंग
    0.40
    îne
    0.38
    ignant
    0.38
    ){}^
    0.37
    /******/
    0.37
    striction
    0.37
     мясо
    0.36
     hyperplasia
    0.36
    oult
    0.36
    PURE
    0.35
    POSITIVE LOGITS
     arc
    0.74
     Arc
    0.61
    Arc
    0.59
     arcs
    0.58
     rc
    0.55
    arc
    0.55
     ARC
    0.54
     Rc
    0.50
     RC
    0.50
    Rc
    0.50
    Act Density 0.004%

    No Known Activations