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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    áč
    -0.07
     Bride
    -0.07
    legal
    -0.07
    یر
    -0.06
    _side
    -0.06
    LOTS
    -0.06
    locker
    -0.06
     Caul
    -0.06
     Rach
    -0.06
    Keeper
    -0.06
    POSITIVE LOGITS
    (env
    0.07
    jn
    0.06
     pricing
    0.06
     fj
    0.06
    activity
    0.06
    XXXX
    0.06
     t
    0.06
    }while
    0.06
    .xhtml
    0.06
     адміністратив
    0.06
    Act Density 0.479%

    No Known Activations