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

    Neuronpedia

    INDEX
    Explanations

    causal relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Aner
    0.42
    मेड
    0.38
    嘯
    0.36
     갔
    0.36
    Spin
    0.35
    Medical
    0.35
    Democratic
    0.35
    went
    0.34
     İst
    0.34
    вид
    0.34
    POSITIVE LOGITS
    中山
    0.37
    Matcher
    0.35
    地形
    0.34
    সই
    0.34
    entos
    0.34
     mule
    0.34
    ‍
    0.33
    可以通过
    0.33
     nigga
    0.33
     kandi
    0.33
    Act Density 0.000%

    No Known Activations