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

    Neuronpedia

    INDEX
    Explanations

    conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    udging
    -0.08
     defining
    -0.07
    もし
    -0.06
    ']]↵
    -0.06
    inition
    -0.06
    准
    -0.06
    如何
    -0.06
     mortal
    -0.06
    $f
    -0.06
    岁
    -0.06
    POSITIVE LOGITS
     robot
    0.07
    TouchListener
    0.07
     weiter
    0.06
    prene
    0.06
    CONDS
    0.06
     triangles
    0.06
     Deadline
    0.06
     confirmed
    0.06
     distributors
    0.06
     corrobor
    0.06
    Act Density 0.006%

    No Known Activations