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

    Neuronpedia

    INDEX
    Explanations

    objects and processes in systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wretched
    0.60
     sadistic
    0.56
     demonic
    0.54
     ridiculous
    0.51
     haught
    0.51
     gruesome
    0.50
     monstru
    0.50
     estrange
    0.50
     reeks
    0.49
     heinous
    0.49
    POSITIVE LOGITS
    λ
    0.38
    oconut
    0.36
    Application
    0.35
    transform
    0.35
    widgetTo
    0.35
    安全
    0.35
    Client
    0.34
    Village
    0.34
    )$
    0.33
    Proposal
    0.33
    Act Density 0.064%

    No Known Activations