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

    Neuronpedia

    INDEX
    Explanations

    flow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    سن
    -0.06
    رس
    -0.06
    итом
    -0.06
     обра
    -0.06
    äd
    -0.06
    Hen
    -0.06
     strstr
    -0.06
    endet
    -0.06
     democr
    -0.06
     čer
    -0.06
    POSITIVE LOGITS
     ترک
    0.07
    Chris
    0.06
    (spell
    0.06
     stint
    0.06
    _checked
    0.06
    ks
    0.06
    _KEY
    0.06
    猫
    0.06
    VF
    0.06
    _predict
    0.06
    Act Density 0.000%

    No Known Activations