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

    Neuronpedia

    INDEX
    Explanations

    character and sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    asp
    0.49
    oss
    0.48
    ová
    0.48
    öh
    0.47
    öst
    0.45
    GEST
    0.45
    AMPLES
    0.45
    künd
    0.45
    aby
    0.45
    izz
    0.45
    POSITIVE LOGITS
    นี้
    0.51
     جمهوری
    0.48
     یق
    0.47
    下の
    0.47
    Когда
    0.46
    оне
    0.46
    은
    0.45
    شر
    0.44
    Cuba
    0.44
    ጠበ
    0.44
    Act Density 0.000%

    No Known Activations