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

    Neuronpedia

    INDEX
    Explanations

    specific named entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.64
     metadata
    0.63
     DHCP
    0.62
     solvers
    0.62
     waveforms
    0.59
     workflows
    0.58
     analogues
    0.58
    ות
    0.57
     histogram
    0.56
     databases
    0.56
    POSITIVE LOGITS
    A
    0.63
    ita
    0.61
    ito
    0.60
    ano
    0.60
    ond
    0.59
    á
    0.59
    leq
    0.58
    ä
    0.58
    č
    0.58
    phi
    0.58
    Act Density 0.106%

    No Known Activations