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

    Neuronpedia

    INDEX
    Explanations

    symbols and characters related to file and directory management

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

    URL parameters or paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    houette
    -0.42
    lihood
    -0.40
     Chalet
    -0.40
    jména
    -0.39
     bahía
    -0.39
    hloromethane
    -0.39
     Surely
    -0.38
     kaarangay
    -0.38
    Ligações
    -0.38
    Bakgrunnsstoff
    -0.38
    POSITIVE LOGITS
    =:
    1.19
    =%
    1.19
    =_
    1.18
    =?
    1.13
    =/
    1.13
    =@
    1.11
    =$
    1.09
    =*
    1.07
    =?,
    1.06
    =[
    1.02
    Act Density 0.026%

    No Known Activations