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

    Neuronpedia

    INDEX
    Explanations

    infinitives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igidBody
    -0.06
    edeki
    -0.06
     mùa
    -0.06
     ultr
    -0.06
     kle
    -0.06
     доступ
    -0.06
    ặt
    -0.06
     gef
    -0.06
    >&
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    Safety
    0.08
     Caesar
    0.06
     CLEAN
    0.06
     같다
    0.06
    _Widget
    0.06
    	cd
    0.06
    Records
    0.06
    _Record
    0.06
    SERVER
    0.06
    _str
    0.06
    Act Density 0.108%

    No Known Activations