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

    Neuronpedia

    INDEX
    Explanations

    words containing "ow" or "aw" with a bias towards homophones

    oai_token-act-pair · gemini-2.0-flash

    sewing and teaching

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UnknownFieldSet
    -0.57
    apimachinery
    -0.55
    enumii
    -0.54
    URLException
    -0.54
    zarchiwizowane
    -0.51
     محفوظة
    -0.50
     jadx
    -0.50
    Portale
    -0.50
    :][
    -0.49
    ANTLR
    -0.48
    POSITIVE LOGITS
    0.71
    jalá
    0.58
     AssemblyVersion
    0.55
    олові
    0.55
    ebx
    0.55
     čierna
    0.54
    rensen
    0.53
    ^(@)
    0.53
    dhury
    0.53
    arden
    0.52
    Act Density 0.356%

    No Known Activations