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

    Neuronpedia

    INDEX
    Explanations

    Either

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -cost
    -0.07
     chase
    -0.06
    ICA
    -0.06
    68
    -0.06
    Ngoài
    -0.06
    Skip
    -0.06
    great
    -0.06
     snakes
    -0.06
    Great
    -0.06
    名前
    -0.06
    POSITIVE LOGITS
    (tr
    0.07
    Outlined
    0.07
    ักษณะ
    0.07
     tcb
    0.07
     TLabel
    0.06
    .Struct
    0.06
    (getContext
    0.06
     deciding
    0.06
    (tid
    0.06
    álu
    0.06
    Act Density 0.127%

    No Known Activations