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

    Neuronpedia

    INDEX
    Explanations

    Scientific/technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hal
    -0.07
    ADDE
    -0.06
    619
    -0.06
    燕
    -0.06
     Humb
    -0.06
    illance
    -0.06
     Hal
    -0.06
     porch
    -0.06
     xnxx
    -0.06
     ύ
    -0.06
    POSITIVE LOGITS
    (names
    0.07
     candidate
    0.07
     phishing
    0.06
    003
    0.06
    Match
    0.06
     unrecognized
    0.06
    jax
    0.06
     fraction
    0.06
    %.
    0.06
     clearer
    0.06
    Act Density 0.001%

    No Known Activations