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

    Neuronpedia

    INDEX
    Explanations

    Install

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _extent
    -0.07
    ari
    -0.07
     AX
    -0.07
     pensions
    -0.07
     applicants
    -0.07
    Funny
    -0.07
    NI
    -0.06
     SIP
    -0.06
    _layer
    -0.06
     ax
    -0.06
    POSITIVE LOGITS
     cải
    0.07
     sebeb
    0.06
    0.06
     besie
    0.06
    (xy
    0.06
     тиж
    0.06
     Lös
    0.06
     Yaş
    0.06
     Tel
    0.06
    querque
    0.06
    Act Density 0.106%

    No Known Activations