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

    Neuronpedia

    INDEX
    Explanations

    salesman

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yu
    -0.07
    >
    -0.06
     jugar
    -0.06
    ар
    -0.06
    دار
    -0.06
    _via
    -0.06
     reversing
    -0.06
    uk
    -0.06
    센
    -0.05
    (&(
    -0.05
    POSITIVE LOGITS
    과정
    0.07
    .Inventory
    0.07
    ِل
    0.07
    lb
    0.06
     careful
    0.06
     genres
    0.06
    dent
    0.06
    _alive
    0.06
    Primitive
    0.06
    紹
    0.06
    Act Density 0.007%

    No Known Activations