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

    Neuronpedia

    INDEX
    Explanations

    ip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ped
    -0.07
     layui
    -0.07
     χρή
    -0.06
     narr
    -0.06
    EF
    -0.06
    Project
    -0.06
    acies
    -0.06
    layui
    -0.06
     　 　 　 　 　 　
    -0.06
     uterus
    -0.06
    POSITIVE LOGITS
     hommes
    0.07
     brilliantly
    0.06
     outdoors
    0.06
    .putInt
    0.06
     Joker
    0.06
     стар
    0.06
     charg
    0.06
    قات
    0.06
     뛰
    0.06
     coup
    0.06
    Act Density 0.002%

    No Known Activations