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

    Neuronpedia

    INDEX
    Explanations

    grant access or permission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     razón
    0.47
     బల
    0.44
     Pov
    0.43
    బ
    0.43
    ذ
    0.42
    υνα
    0.42
    धक
    0.42
    Sh
    0.40
    ભગ
    0.40
    ियल
    0.40
    POSITIVE LOGITS
     granted
    0.59
     permission
    0.58
     grant
    0.56
     concessions
    0.56
     concession
    0.55
     grants
    0.54
     granting
    0.54
     access
    0.54
     permisos
    0.53
    grant
    0.52
    Act Density 0.010%

    No Known Activations