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

    Neuronpedia

    INDEX
    Explanations

    inhibitory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resil
    -0.08
     congestion
    -0.07
     بتن
    -0.07
    /devices
    -0.07
    isnan
    -0.07
     sollen
    -0.07
    िसस
    -0.06
     titten
    -0.06
     bullpen
    -0.06
     desn
    -0.06
    POSITIVE LOGITS
    ory
    0.08
    ORY
    0.08
    odial
    0.08
     LDAP
    0.08
     допомоги
    0.07
     Ry
    0.07
    NDAR
    0.07
    MR
    0.07
     regulatory
    0.07
    Y
    0.07
    Act Density 0.037%

    No Known Activations