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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nab
    -0.07
     goodbye
    -0.07
     petrol
    -0.07
    _without
    -0.07
     Nab
    -0.06
    �
    -0.06
     liter
    -0.06
     techn
    -0.06
     VIR
    -0.06
     SEG
    -0.06
    POSITIVE LOGITS
    ое
    0.08
     Trojan
    0.07
     üyeler
    0.07
    教练
    0.07
    stacle
    0.07
    -feedback
    0.07
     mógł
    0.07
    ians
    0.07
     Hunters
    0.06
    ъем
    0.06
    Act Density 0.006%

    No Known Activations