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

    Neuronpedia

    INDEX
    Explanations

    Matrix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    žený
    -0.07
     Burg
    -0.07
    เภ
    -0.06
    /gin
    -0.06
     overwritten
    -0.06
    잖
    -0.06
    čně
    -0.06
     згад
    -0.06
    .swap
    -0.06
     yếu
    -0.06
    POSITIVE LOGITS
     scaffold
    0.07
    noticed
    0.07
     Broadcast
    0.07
     LSU
    0.06
     관련
    0.06
     escalate
    0.06
    /ubuntu
    0.06
     mote
    0.06
     transient
    0.06
    htar
    0.06
    Act Density 0.028%

    No Known Activations