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

    Neuronpedia

    INDEX
    Explanations

    negatively connoted terms related to new developments or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words starting with "un" or "once"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.55
     autorytatywna
    -0.51
     HasFactory
    -0.49
     estekak
    -0.46
    arangay
    -0.45
     fijo
    -0.44
    pecabe
    -0.42
     didReceive
    -0.40
    ngrx
    -0.40
    ientras
    -0.40
    POSITIVE LOGITS
     RZ
    0.52
    unct
    0.50
    gris
    0.49
    omni
    0.49
    riad
    0.49
     biologic
    0.49
    Pfalz
    0.49
     (!!
    0.49
    unitas
    0.48
    たって
    0.47
    Act Density 0.007%

    No Known Activations