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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     perfection
    -0.09
    来说
    -0.08
     already
    -0.08
     cały
    -0.08
    already
    -0.07
    จะ
    -0.07
     holiness
    -0.07
    め
    -0.07
    어
    -0.07
     �
    -0.07
    POSITIVE LOGITS
    -ish
    0.12
     teilweise
    0.11
     تقريب
    0.11
     appreci
    0.11
     כמעט
    0.11
     parcialmente
    0.11
     largely
    0.10
     partly
    0.10
     sebagian
    0.10
     prácticamente
    0.09
    Act Density 0.079%

    No Known Activations