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

    Neuronpedia

    INDEX
    Explanations

    OpenWRT, discourse, forums

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ambienti
    0.42
    巽
    0.41
    rypsin
    0.38
    ToJava
    0.38
    ":"","
    0.37
     ':'
    0.36
    ཊ
    0.36
    }}}{\
    0.35
    тивным
    0.35
    adoop
    0.35
    POSITIVE LOGITS
     forum
    0.47
     spoiled
    0.46
     Forum
    0.46
    论坛
    0.45
     @
    0.45
     orchard
    0.44
     topic
    0.44
     Topic
    0.43
    Forum
    0.42
    Topic
    0.41
    Act Density 0.005%

    No Known Activations