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

    Neuronpedia

    INDEX
    Explanations

    famous people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     گیند
    0.38
    Dieser
    0.37
    இந்த
    0.36
    竻
    0.35
     mengakses
    0.34
     девя
    0.34
     ഇപ്പോൾ
    0.34
    𒄿
    0.34
     anzeigen
    0.34
    форд
    0.34
    POSITIVE LOGITS
     personas
    0.43
     kriminal
    0.40
     políticos
    0.40
     and
    0.39
     economic
    0.38
    political
    0.36
    bridge
    0.35
     collectives
    0.35
    api
    0.35
     malicious
    0.35
    Act Density 0.001%

    No Known Activations