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

    Neuronpedia

    INDEX
    Explanations

    Hugging Face, Humane Society, Hyprland

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ㄽ
    0.50
     ล
    0.49
    Så
    0.49
    Detectable
    0.46
    RestorePolicy
    0.46
    Fund
    0.45
    infodisc
    0.45
    MyToolkit
    0.44
    ้วน
    0.43
    Configuration
    0.43
    POSITIVE LOGITS
     h
    0.53
     LH
    0.50
     HHS
    0.49
     HL
    0.44
     H
    0.43
     UH
    0.41
     HSP
    0.41
     AH
    0.40
     HSA
    0.40
     HE
    0.40
    Act Density 0.112%

    No Known Activations