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

    Neuronpedia

    INDEX
    Explanations

    VRAM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mar
    0.42
     Mar
    0.42
     mar
    0.41
    pfl
    0.41
     Gr
    0.40
    Gr
    0.39
    Grain
    0.38
    cks
    0.38
     Гор
    0.36
    Гор
    0.36
    POSITIVE LOGITS
     amines
    0.40
     ros
    0.39
     promoc
    0.38
     amino
    0.38
     ры
    0.38
    山口
    0.37
     mah
    0.37
     abusive
    0.37
     Promotion
    0.36
    Amino
    0.36
    Act Density 0.006%

    No Known Activations