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

    Neuronpedia

    INDEX
    Explanations

    proportionate relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    峩
    0.54
    <unused988>
    0.54
    ни
    0.50
    clerosis
    0.47
     responsabil
    0.46
     Instrum
    0.46
    甪
    0.46
    罣
    0.46
    áln
    0.45
    䨋
    0.45
    POSITIVE LOGITS
    0.65
     (
    0.58
     from
    0.55
     around
    0.53
     DS
    0.47
     Max
    0.44
     experience
    0.43
     Terry
    0.43
     않았
    0.42
     extracted
    0.41
    Act Density 0.003%

    No Known Activations