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

    Neuronpedia

    INDEX
    Explanations

    increase purchase quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Manufacturing
    0.49
     médicament
    0.48
     형태
    0.47
    ப்புக்
    0.41
    ပုံ
    0.40
    Manufacturing
    0.39
    㳓
    0.39
    王
    0.39
    araan
    0.38
     본
    0.38
    POSITIVE LOGITS
    enable
    0.43
     flocks
    0.39
    Enable
    0.39
    º
    0.38
     sentir
    0.38
     also
    0.38
     flock
    0.38
     EOF
    0.37
    ]?.
    0.37
    EO
    0.36
    Act Density 0.000%

    No Known Activations