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

    Neuronpedia

    INDEX
    Explanations

    triple back ticks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wretched
    0.55
     horrid
    0.46
     kombin
    0.45
     sinner
    0.45
     spo
    0.44
     vehement
    0.43
     wrongfully
    0.43
     takt
    0.43
     mixtape
    0.43
     rychle
    0.42
    POSITIVE LOGITS
    organisms
    0.51
    DBMS
    0.48
    Constraint
    0.47
    default
    0.46
    amsmath
    0.46
    Root
    0.46
    权限
    0.46
    API
    0.46
    Permissions
    0.46
    Debug
    0.45
    Act Density 0.005%

    No Known Activations