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

    Neuronpedia

    INDEX
    Explanations

    Questions, instructions, explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LBL
    -0.06
     rg
    -0.06
    asin
    -0.06
    signIn
    -0.06
    RN
    -0.06
    sterol
    -0.06
    ㏃
    -0.06
    ROLL
    -0.06
    ARB
    -0.06
    未必
    -0.06
    POSITIVE LOGITS
    -loving
    0.07
     unspecified
    0.07
    .spatial
    0.07
    .matches
    0.07
    こんにちは
    0.07
     adjoining
    0.07
    יאות
    0.07
     After
    0.07
     중요
    0.07
    忽悠
    0.07
    Act Density 0.290%

    No Known Activations