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

    Neuronpedia

    INDEX
    Explanations

    stable, able

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,null
    -0.07
     Lee
    -0.07
    _matrices
    -0.06
    329
    -0.06
    ift
    -0.06
     kür
    -0.06
    _MAT
    -0.06
    	md
    -0.06
     REC
    -0.06
    /docker
    -0.06
    POSITIVE LOGITS
     Stable
    0.17
     stable
    0.13
    stable
    0.10
     ميل
    0.07
    716
    0.07
    alter
    0.06
    ables
    0.06
     substantially
    0.06
    Ability
    0.06
     segmented
    0.06
    Act Density 0.005%

    No Known Activations