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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ataset
    -0.07
    iffany
    -0.07
    owie
    -0.06
     velký
    -0.06
    renched
    -0.06
    rient
    -0.06
     hmm
    -0.06
     personally
    -0.06
     decryption
    -0.06
     Carry
    -0.06
    POSITIVE LOGITS
    Assertion
    0.08
     kin
    0.07
     Assertion
    0.07
     Astroph
    0.06
    duk
    0.06
     contends
    0.06
    Runnable
    0.06
    攻
    0.06
     Args
    0.06
    提示
    0.06
    Act Density 0.000%

    No Known Activations