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

    Neuronpedia

    INDEX
    Explanations

    de

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Block
    -0.07
    k
    -0.07
     Spirits
    -0.07
    nk
    -0.06
    ks
    -0.06
     ничего
    -0.06
     millennials
    -0.06
    _k
    -0.06
     Cycl
    -0.06
     Nightmare
    -0.06
    POSITIVE LOGITS
     �
    0.07
    �細
    0.07
    vf
    0.07
     �
    0.07
    _REFERER
    0.07
    .PostMapping
    0.07
     possess
    0.07
     SignUp
    0.06
    bfd
    0.06
    .'.
    0.06
    Act Density 0.040%

    No Known Activations