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

    Neuronpedia

    INDEX
    Explanations

    receiver

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stop
    -0.08
    transpose
    -0.08
    stmt
    -0.07
    Stay
    -0.07
    .documentElement
    -0.07
    ////////
    -0.07
    scope
    -0.07
    dhcp
    -0.07
    ☂
    -0.07
    losure
    -0.07
    POSITIVE LOGITS
    枅
    0.07
     phiếu
    0.07
    醫療
    0.06
     araştırma
    0.06
    ᆨ
    0.06
     LB
    0.06
     erro
    0.06
     SS
    0.06
     mailing
    0.06
     Atari
    0.06
    Act Density 0.000%

    No Known Activations