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

    Neuronpedia

    INDEX
    Explanations

    beginners and novices

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TEXT
    -0.07
     Ginger
    -0.07
     measurement
    -0.07
    BUFFER
    -0.06
     internacional
    -0.06
     Ev
    -0.06
    89
    -0.06
     Projects
    -0.06
    76
    -0.06
     Factors
    -0.06
    POSITIVE LOGITS
    mando
    0.07
    ΑΡ
    0.07
    rego
    0.06
    ěj
    0.06
    ула
    0.06
    AUD
    0.06
    _OscInitStruct
    0.06
     чуж
    0.06
     ikke
    0.06
    uteur
    0.06
    Act Density 0.035%

    No Known Activations