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

    Neuronpedia

    INDEX
    Explanations

    Reboot Nation resource

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    אס
    0.43
    ERTS
    0.42
    Van
    0.42
    罗斯
    0.40
    VAN
    0.39
    assertArg
    0.39
    Psalm
    0.39
    Nic
    0.38
    Nik
    0.38
    Pole
    0.37
    POSITIVE LOGITS
     sexually
    0.38
     Shepherd
    0.36
    endien
    0.35
     kec
    0.35
     ot
    0.34
     dil
    0.34
    켜
    0.34
     qu
    0.34
     cor
    0.33
     overhead
    0.33
    Act Density 0.013%

    No Known Activations