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

    Neuronpedia

    INDEX
    Explanations

    introduces topic followed by duration or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    が得
    0.38
     пле
    0.38
    꽃
    0.37
    Plas
    0.36
     ple
    0.36
    Vg
    0.36
    لوار
    0.35
    老爷
    0.35
    کلی
    0.35
    ன்களை
    0.35
    POSITIVE LOGITS
     ISR
    0.40
     মনি
    0.40
    ramine
    0.39
     WSA
    0.39
     Berkshire
    0.39
    Minute
    0.38
     Minn
    0.38
    propan
    0.37
     Wizards
    0.37
     தகவல்
    0.37
    Act Density 0.000%

    No Known Activations