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

    Neuronpedia

    INDEX
    Explanations

    teleport

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ft
    -0.07
     Jedi
    -0.07
    directive
    -0.06
     zastav
    -0.06
     zh
    -0.06
     믿
    -0.06
     Больш
    -0.06
     získal
    -0.06
    _CHANNELS
    -0.06
     ';↵↵
    -0.06
    POSITIVE LOGITS
    acula
    0.07
     pulling
    0.06
    َأ
    0.06
    فق
    0.06
    .MiddleCenter
    0.06
     misog
    0.06
     misogyn
    0.06
    ATO
    0.06
    Invocation
    0.06
     Figure
    0.06
    Act Density 0.000%

    No Known Activations