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

    Neuronpedia

    INDEX
    Explanations

    Dockerfile or shader

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⚤
    0.44
     bumi
    0.39
    IFORNIA
    0.37
     कारो
    0.37
    ANSAS
    0.36
     ASSEMBLY
    0.36
    埄
    0.36
    䒷
    0.35
    Equipo
    0.35
     યો
    0.35
    POSITIVE LOGITS
    ofar
    0.41
    agio
    0.39
     $:=$
    0.38
     nello
    0.37
    ardo
    0.36
    hd
    0.35
     बच्चा
    0.35
    ToggleButton
    0.35
    adhar
    0.35
    rous
    0.34
    Act Density 0.001%

    No Known Activations