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

    Neuronpedia

    INDEX
    Explanations

    directory paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DEVICE
    -0.07
     FILES
    -0.07
     highway
    -0.07
    ová
    -0.07
    ffb
    -0.06
     station
    -0.06
     вет
    -0.06
     DATE
    -0.06
     hoax
    -0.06
    nano
    -0.06
    POSITIVE LOGITS
     GDP
    0.07
    益
    0.06
    �
    0.06
    ิหาร
    0.06
     scop
    0.06
     ambassadors
    0.06
    gar
    0.06
    един
    0.06
     sentir
    0.06
     submitting
    0.06
    Act Density 0.004%

    No Known Activations