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

    Neuronpedia

    INDEX
    Explanations

    things followed by descriptive clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    嚨
    0.42
    EnableCOMDAT
    0.41
    㧕
    0.41
    ㎚
    0.41
    Спољашње
    0.41
    軞
    0.41
    🔟
    0.41
    隂
    0.39
    securityMarks
    0.39
    ⚌
    0.39
    POSITIVE LOGITS
     H
    0.54
     J
    0.48
     q
    0.47
     i
    0.46
     k
    0.46
     g
    0.45
    M
    0.44
    H
    0.44
     y
    0.44
     z
    0.44
    Act Density 0.000%

    No Known Activations