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

    Neuronpedia

    INDEX
    Explanations

    common phrases and expressions regarding opinions and thoughts

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

    I think it was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cerpt
    -0.47
     nakalista
    -0.46
    posedge
    -0.42
     mxArray
    -0.42
     betweenstory
    -0.41
     Salgado
    -0.39
    tonode
    -0.39
    IVEREF
    -0.38
     cerrada
    -0.38
    EndInit
    -0.37
    POSITIVE LOGITS
     think
    0.57
     THINK
    0.56
    Think
    0.56
    THINK
    0.55
    น่า
    0.54
    MENAFN
    0.54
    think
    0.52
     Think
    0.52
    RectangleBorder
    0.50
    ควร
    0.49
    Act Density 0.051%

    No Known Activations