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

    Neuronpedia

    INDEX
    Explanations

    assertions of correctness or validity in statements

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

    acknowledging a point or agreement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.48
     bricolaje
    -0.42
     transfieras
    -0.42
     mijne
    -0.39
    InputBorder
    -0.37
     čierna
    -0.36
     beweging
    -0.36
    pgterms
    -0.36
    erçe
    -0.36
     vụ
    -0.36
    POSITIVE LOGITS
    SequentialGroup
    0.50
    StructEnd
    0.49
    RTEX
    0.46
    っしゃ
    0.43
     MainAxisSize
    0.42
    MIDDLEWARE
    0.41
    ResumeLayout
    0.40
    Referanser
    0.40
    GOTREF
    0.40
     pega
    0.40
    Act Density 0.070%

    No Known Activations