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

    Neuronpedia

    INDEX
    Explanations

    Northern

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lash
    -0.28
     Anthrop
    -0.26
    irit
    -0.26
    è¿İåIJĪ
    -0.26
    ltr
    -0.26
    .appspot
    -0.25
     Vanderbilt
    -0.25
    iller
    -0.24
    åĪĿ
    -0.24
    ressed
    -0.24
    POSITIVE LOGITS
     Pipes
    0.27
    åĬŁè¯¾
    0.26
     She
    0.25
    åİ»çľĭçľĭ
    0.25
    Cascade
    0.25
     dru
    0.25
    èĽĢ
    0.25
     resultant
    0.24
    人åı£
    0.24
     menu
    0.24
    Act Density 0.015%

    No Known Activations