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

    Neuronpedia

    INDEX
    Explanations

    themes related to change and contrasting viewpoints

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

    sudden changes in opinion or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.59
     незавершена
    -0.57
     autorytatywna
    -0.57
     snippetHide
    -0.52
    SharedCtor
    -0.50
    astify
    -0.49
    Ligações
    -0.48
    WireFormat
    -0.47
    +#+#
    -0.47
     الرياضيه
    -0.47
    POSITIVE LOGITS
     swing
    0.39
     turnaround
    0.36
     plötzlich
    0.35
     suddenly
    0.35
     swings
    0.32
    SystemColors
    0.32
     quickly
    0.32
    swing
    0.32
    汰
    0.32
     sudden
    0.31
    Act Density 0.128%

    No Known Activations