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

    Neuronpedia

    INDEX
    Explanations

    statistical correlations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quiry
    -0.07
    ineTransform
    -0.07
    icism
    -0.06
    .of
    -0.06
    それは
    -0.06
    Patrick
    -0.06
    џџџџџџџџџџџџџџџџџџџџџџџџџџџџџџџџ
    -0.06
     privat
    -0.06
    licenses
    -0.06
    UILTIN
    -0.06
    POSITIVE LOGITS
     extortion
    0.08
    .console
    0.06
     excellent
    0.06
     titanium
    0.06
     Fired
    0.06
     Think
    0.06
     Russians
    0.06
     compiling
    0.06
     decreases
    0.06
     Intercept
    0.06
    Act Density 0.005%

    No Known Activations