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

    Neuronpedia

    INDEX
    Explanations

    believe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Station
    -0.07
     dışı
    -0.07
     piano
    -0.07
     harder
    -0.06
    Map
    -0.06
    茂
    -0.06
     výstav
    -0.06
     roundup
    -0.06
    _forward
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     believed
    0.10
     believe
    0.09
     believes
    0.08
     비
    0.07
     Bel
    0.07
    BP
    0.07
     beliefs
    0.06
    NI
    0.06
    vous
    0.06
    �
    0.06
    Act Density 0.025%

    No Known Activations