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

    Neuronpedia

    INDEX
    Explanations

    stranger danger, strange stars, fatherland

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಪೊಲೀ
    0.42
    غان
    0.41
    kra
    0.40
     jellyfish
    0.39
    لاع
    0.39
    監
    0.39
    蚜
    0.38
     സേ
    0.38
     focal
    0.38
    東海
    0.38
    POSITIVE LOGITS
     Mixed
    0.40
     Cout
    0.40
     Cin
    0.40
     Chau
    0.38
     Juin
    0.38
     DV
    0.37
     King
    0.37
     Quinn
    0.37
     Quin
    0.37
    čas
    0.36
    Act Density 0.000%

    No Known Activations