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

    Neuronpedia

    INDEX
    Explanations

    opinions, beliefs and disagreements.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'hold'

    np_token-act-pair-logits · gpt-4o-mini

    hold

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лтамалар
    -0.57
    zeba
    -0.53
    Rüyada
    -0.52
     jsPsych
    -0.52
    findpost
    -0.51
    ьаж
    -0.50
    částí
    -0.48
    uttavia
    -0.47
    bondale
    -0.47
    sendRedirect
    -0.46
    POSITIVE LOGITS
     held
    1.55
    held
    1.50
     hold
    1.38
     holds
    1.32
     holding
    1.26
     Hold
    1.26
    Holding
    1.25
     Holding
    1.23
    Hold
    1.23
    hold
    1.23
    Act Density 1.692%

    No Known Activations