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

    Neuronpedia

    INDEX
    Explanations

    references to information disclosure and privacy issues

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

    publication and identity disclosure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bie
    -0.39
     Currie
    -0.37
    oda
    -0.34
    ,
    -0.33
    Subview
    -0.33
    +:+
    -0.33
     Calvo
    -0.31
     cobran
    -0.31
     escur
    -0.31
    estine
    -0.31
    POSITIVE LOGITS
    twimg
    0.77
    IntoConstraints
    0.71
     rhestr
    0.66
     Photocase
    0.64
     Roskov
    0.63
     Autorisations
    0.62
     autorytatywna
    0.61
     disambiguazione
    0.59
     gyhoeddwyd
    0.59
    oa̍t
    0.59
    Act Density 0.019%

    No Known Activations