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

    Neuronpedia

    INDEX
    Explanations

    string

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (flow
    -0.07
    _balance
    -0.07
    ичної
    -0.06
    _pause
    -0.06
    _conn
    -0.06
    -dependent
    -0.06
    dog
    -0.06
    ینک
    -0.06
    ische
    -0.06
     cracks
    -0.06
    POSITIVE LOGITS
    !');↵
    0.06
     tendon
    0.06
     '',↵
    0.06
    quires
    0.06
    .’”↵↵
    0.06
     UserName
    0.06
    })↵↵
    0.06
     lodging
    0.06
    ;↵↵
    0.06
     ");
↵
    0.06
    Act Density 0.003%

    No Known Activations