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

    Neuronpedia

    INDEX
    Explanations

    expressions and concepts related to constancy and fixed values

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

    constant or fixed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.51
    {{/
    -0.37
    rett
    -0.35
    criminator
    -0.35
    -------
    -0.35
    uda
    -0.34
     تضيفلها
    -0.33
    xhttp
    -0.33
    Intersect
    -0.32
    later
    -0.32
    POSITIVE LOGITS
     Constant
    0.82
     constant
    0.81
     fixed
    0.81
    constant
    0.79
     constantes
    0.76
     Fixed
    0.73
     constante
    0.73
    fixed
    0.73
    Fixed
    0.73
    Constant
    0.71
    Act Density 0.209%

    No Known Activations