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

    Neuronpedia

    INDEX
    Explanations

    Creating holes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pwd
    -0.07
     meter
    -0.06
     Joseph
    -0.06
    Webpack
    -0.06
    Joseph
    -0.06
    PROFILE
    -0.06
    .icon
    -0.06
    Playlist
    -0.06
     ob
    -0.06
     сх
    -0.06
    POSITIVE LOGITS
    	ASSERT
    0.07
     عملیات
    0.07
    ق
    0.06
    aura
    0.06
    ällt
    0.06
    신
    0.06
    áveis
    0.06
    lerdi
    0.06
    (ع
    0.06
     عالم
    0.06
    Act Density 0.036%

    No Known Activations