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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Euro
    -0.06
    ("/")
    -0.06
    .tele
    -0.06
    ��
    -0.06
     Sele
    -0.06
     skype
    -0.06
     ру
    -0.06
    .Manager
    -0.06
     thems
    -0.05
    belie
    -0.05
    POSITIVE LOGITS
     plaque
    0.08
     agrees
    0.07
     %↵↵
    0.07
     fitting
    0.07
     missile
    0.07
     Missile
    0.07
     اض
    0.06
    起こ
    0.06
     annoyance
    0.06
    _probs
    0.06
    Act Density 0.006%

    No Known Activations