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

    Neuronpedia

    INDEX
    Explanations

    town

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Di
    -0.08
    уры
    -0.08
     čtyř
    -0.07
     Mercy
    -0.07
    elif
    -0.07
    liter
    -0.07
    mare
    -0.06
    bytes
    -0.06
     rigor
    -0.06
    cdf
    -0.06
    POSITIVE LOGITS
     Town
    0.13
     town
    0.12
     towns
    0.10
    Town
    0.10
     Townsend
    0.08
    town
    0.07
    なんだ
    0.07
     TN
    0.07
     VT
    0.07
    OWN
    0.07
    Act Density 0.016%

    No Known Activations