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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    owel
    -0.07
     Semaphore
    -0.06
     HLS
    -0.06
     сос
    -0.06
    ymax
    -0.06
    getClient
    -0.06
    -medium
    -0.06
     lug
    -0.06
    _QU
    -0.06
    "She
    -0.06
    POSITIVE LOGITS
    Policy
    0.07
     expectations
    0.07
    .env
    0.06
    _nm
    0.06
     }}
↵
    0.06
     staggering
    0.06
    DU
    0.06
    jections
    0.06
     tackling
    0.06
     }
↵
↵
    0.06
    Act Density 0.000%

    No Known Activations