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

    Neuronpedia

    INDEX
    Explanations

    phrases and keywords related to conditions or membership within a set

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

    in or not in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.50
     Manns
    -0.50
    fjspx
    -0.48
    CppMethod
    -0.47
    hastly
    -0.42
    Assume
    -0.41
    FieldOffsetTable
    -0.40
     avoient
    -0.40
    Hilsen
    -0.39
    Planta
    -0.38
    POSITIVE LOGITS
    notin
    0.53
    ∉
    0.51
     among
    0.49
     wśród
    0.47
    rungsseite
    0.47
    NotIn
    0.46
    toContain
    0.44
    glTexCoord
    0.43
    IsIn
    0.43
     inclusions
    0.43
    Act Density 0.263%

    No Known Activations