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

    Neuronpedia

    INDEX
    Explanations

    -one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ']))↵
    -0.08
    })↵↵
    -0.07
     Implicit
    -0.07
    ])
↵
    -0.06
    }]↵
    -0.06
    φυ
    -0.06
    니까
    -0.06
    ↵        ↵
    -0.06
    음을
    -0.06
     Floors
    -0.06
    POSITIVE LOGITS
     doorway
    0.06
    upgrade
    0.06
    -entity
    0.06
     constituent
    0.06
     درب
    0.06
    -esteem
    0.06
    rror
    0.06
    ultimate
    0.06
     interle
    0.06
     اسپ
    0.06
    Act Density 0.005%

    No Known Activations