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

    Neuronpedia

    INDEX
    Explanations

    code and ASCII art

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    入选
    -0.07
    sig
    -0.07
    잖아
    -0.07
    込む
    -0.07
    те
    -0.07
    zung
    -0.06
    wav
    -0.06
    דלק
    -0.06
     Finland
    -0.06
    rax
    -0.06
    POSITIVE LOGITS
     בלי
    0.07
    假设
    0.07
    这句话
    0.07
    _fact
    0.07
     upsetting
    0.07
    }>
    0.07
    */}↵
    0.07
     pointing
    0.07
     pits
    0.06
     BETWEEN
    0.06
    Act Density 0.005%

    No Known Activations