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

    Neuronpedia

    INDEX
    Explanations

    color meta tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ською
    0.41
    ць
    0.40
     Aby
    0.39
     éto
    0.37
    ElementsBy
    0.36
    chien
    0.36
    ?;
    0.36
    境外
    0.36
    境
    0.36
    Aby
    0.35
    POSITIVE LOGITS
     Phas
    0.44
     Josh
    0.44
     recharged
    0.42
     positioning
    0.42
     reincarnation
    0.42
    Josh
    0.40
     recharging
    0.38
     manipulator
    0.38
     bench
    0.38
     ultrasonic
    0.38
    Act Density 0.000%

    No Known Activations