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

    Neuronpedia

    INDEX
    Explanations

    code errors and calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CIO
    -0.08
     unified
    -0.07
     matric
    -0.07
     Gro
    -0.07
    zcze
    -0.07
     реч
    -0.07
     seasons
    -0.07
     Banque
    -0.07
     роз
    -0.07
     candidature
    -0.07
    POSITIVE LOGITS
     �
    0.09
     habilidad
    0.08
     临
    0.08
    )a
    0.08
     Indicates
    0.08
     puck
    0.08
    rena
    0.08
     besitzt
    0.08
     ezin
    0.08
     والمس
    0.08
    Act Density 0.000%

    No Known Activations