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

    Neuronpedia

    INDEX
    Explanations

    hundreds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    11
    -0.09
    14
    -0.08
    6
    -0.08
    7
    -0.07
    10
    -0.07
    13
    -0.07
    06
    -0.07
    22
    -0.07
    09
    -0.07
    3
    -0.07
    POSITIVE LOGITS
     hundreds
    0.08
     Hundreds
    0.07
     har
    0.07
    CORD
    0.07
    ánd
    0.07
    под
    0.07
     ιστο
    0.06
     सम
    0.06
     einf
    0.06
     hafif
    0.06
    Act Density 0.007%

    No Known Activations