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

    Neuronpedia

    INDEX
    Explanations

    our

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HWND
    -0.07
    flo
    -0.07
    	project
    -0.07
     whistlebl
    -0.07
     despair
    -0.07
     poems
    -0.07
     emailAddress
    -0.06
     revive
    -0.06
    하는데
    -0.06
     SNAP
    -0.06
    POSITIVE LOGITS
    染
    0.07
    COLOR
    0.06
    坚果
    0.06
    を見て
    0.06
    攘
    0.06
    Љ
    0.06
     languages
    0.06
    𬶏
    0.06
    _CONNECTION
    0.06
    rente
    0.06
    Act Density 0.205%

    No Known Activations