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

    Neuronpedia

    INDEX
    Explanations

    Mixed text and code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    سط
    -0.07
     ﾞ
    -0.06
    ',↵
    -0.06
     Writer
    -0.06
     Wag
    -0.06
     '')↵
    -0.06
    anim
    -0.06
    ymph
    -0.06
     MAK
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    _vlan
    0.08
    σματα
    0.07
    催
    0.07
    ाई
    0.07
    イル
    0.07
    _WIFI
    0.06
    мель
    0.06
     prostituerte
    0.06
    _PLACE
    0.06
     interception
    0.06
    Act Density 0.005%

    No Known Activations