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

    Neuronpedia

    INDEX
    Explanations

    latex formatting commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ἦ
    0.35
    ือ
    0.34
    awsze
    0.33
    Subtitle
    0.33
    oprote
    0.32
    釦
    0.32
    Regex
    0.32
     peptid
    0.32
    Méd
    0.32
     शैली
    0.32
    POSITIVE LOGITS
     Requested
    0.42
     Considering
    0.40
     Design
    0.36
     Looking
    0.36
     م
    0.36
     Platform
    0.35
     Plantation
    0.35
    0.35
     Machine
    0.35
     but
    0.34
    Act Density 0.002%

    No Known Activations