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

    Neuronpedia

    INDEX
    Explanations

    under specific conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     simpler
    0.45
     panne
    0.42
    Simple
    0.40
     simple
    0.39
    անկ
    0.39
    简单
    0.38
    owl
    0.38
     不需要
    0.38
     hasard
    0.37
     sederhana
    0.37
    POSITIVE LOGITS
     conditional
    1.48
    Conditional
    1.37
     Conditional
    1.36
    conditional
    1.34
     শর্ত
    1.32
    条件
    1.27
     조건
    1.27
     conditionally
    1.26
    條件
    1.25
     condicion
    1.20
    Act Density 0.015%

    No Known Activations