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

    Neuronpedia

    INDEX
    Explanations

    Unboxing/Initial experience

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AP
    -0.07
    .Kind
    -0.07
    ATA
    -0.07
     στη
    -0.07
     graduate
    -0.06
    .af
    -0.06
    čit
    -0.06
    Test
    -0.06
     Isn
    -0.06
    AX
    -0.06
    POSITIVE LOGITS
     sketch
    0.07
     DialogInterface
    0.06
     cess
    0.06
    _SUPPORTED
    0.06
     sketches
    0.06
     "["
    0.06
     �
    0.06
     awakened
    0.06
     Wort
    0.06
    achs
    0.06
    Act Density 0.066%

    No Known Activations