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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    properties
    -0.06
     labour
    -0.06
     Related
    -0.06
    ideo
    -0.06
    >:
    -0.06
     ice
    -0.06
    phase
    -0.06
     varying
    -0.06
    :",
    -0.06
     baker
    -0.06
    POSITIVE LOGITS
     قر
    0.07
     pylint
    0.07
     startX
    0.06
    _ISO
    0.06
    bc
    0.06
    dq
    0.06
    меч
    0.06
     πρω
    0.06
    énom
    0.06
     εκεί
    0.06
    Act Density 0.004%

    No Known Activations