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

    Neuronpedia

    INDEX
    Explanations

    health and security states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ጺ
    0.39
     જુ
    0.39
    表面
    0.36
    licenses
    0.36
     previamente
    0.35
    currentUser
    0.35
     ThemeData
    0.35
    实的
    0.34
     overseen
    0.34
     Riverside
    0.34
    POSITIVE LOGITS
     Bom
    0.42
     continuum
    0.41
    Tunnel
    0.41
     능
    0.41
    idł
    0.41
     ect
    0.40
     Flam
    0.40
    Desc
    0.40
     polit
    0.39
    Lun
    0.39
    Act Density 0.001%

    No Known Activations