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

    Neuronpedia

    INDEX
    Explanations

    vent/hole/tiro

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    egaard
    0.38
     horror
    0.37
     перед
    0.36
     filtro
    0.36
     Filt
    0.36
     Pats
    0.36
     choirs
    0.35
     Employer
    0.35
    affirming
    0.35
     Бет
    0.35
    POSITIVE LOGITS
    ך
    0.34
    ריה
    0.33
    處理
    0.33
    DARK
    0.33
    AUC
    0.31
    AUTH
    0.31
    )
    0.31
    |
    0.30
    Accessibility
    0.30
    0
    0.30
    Act Density 0.008%

    No Known Activations