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

    Neuronpedia

    INDEX
    Explanations

    Handles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Afro
    -0.07
     энерг
    -0.07
     precarious
    -0.07
     infiltration
    -0.06
     Tanks
    -0.06
     сал
    -0.06
     Aeros
    -0.06
     إلي
    -0.06
     indifferent
    -0.06
     сфер
    -0.06
    POSITIVE LOGITS
    !<
    0.07
     disastr
    0.06
     доп
    0.06
    ,L
    0.06
     loại
    0.06
    "]).
    0.06
    ("$.
    0.06
    �
    0.06
    /cmd
    0.06
    (_)
    0.06
    Act Density 0.000%

    No Known Activations