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

    Neuronpedia

    INDEX
    Explanations

    punctuation and conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ip
    -0.07
    erre
    -0.06
     مث
    -0.06
    ored
    -0.06
     posterior
    -0.06
    VIEW
    -0.06
    EO
    -0.06
    metrical
    -0.06
     Ming
    -0.06
    atics
    -0.06
    POSITIVE LOGITS
     Outputs
    0.07
     upt
    0.07
     scipy
    0.07
     expects
    0.07
    Cantidad
    0.07
    _create
    0.07
    楽し
    0.06
     FileSystem
    0.06
    -sp
    0.06
     output
    0.06
    Act Density 0.080%

    No Known Activations