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

    Neuronpedia

    INDEX
    Explanations

    models and their fit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     statutory
    0.84
    ús
    0.73
     polož
    0.73
     stat
    0.73
     beetroot
    0.72
     slats
    0.69
    乃
    0.68
     bırak
    0.68
    addObject
    0.67
     swear
    0.66
    POSITIVE LOGITS
    Multip
    0.91
    Process
    0.89
    Trends
    0.85
    Brief
    0.84
    Mare
    0.83
    ורי
    0.82
    Transient
    0.81
    Kun
    0.81
     ```
    0.81
    хий
    0.81
    Act Density 0.000%

    No Known Activations