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

    Neuronpedia

    INDEX
    Explanations

    code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DOCUMENT
    -0.07
     филь
    -0.06
     ANAL
    -0.06
    MBED
    -0.06
     acquire
    -0.06
     optional
    -0.06
    _DEFINITION
    -0.06
    'label
    -0.06
     З
    -0.06
    "},
    -0.06
    POSITIVE LOGITS
    ｭ
    0.07
     wakeup
    0.07
    ngle
    0.07
     Melbourne
    0.07
    \admin
    0.07
    -door
    0.07
    tau
    0.06
    �
    0.06
    افر
    0.06
    -last
    0.06
    Act Density 0.000%

    No Known Activations