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

    Neuronpedia

    INDEX
    Explanations

    python import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mae
    0.46
     lspace
    0.43
     lst
    0.40
    feng
    0.39
    mae
    0.39
     spez
    0.39
     Castle
    0.38
     extremism
    0.38
     cheating
    0.38
     ship
    0.37
    POSITIVE LOGITS
    ("""
    0.51
    Пор
    0.42
    ("**
    0.42
    """
    0.41
    তির
    0.41
    Portale
    0.41
    订阅
    0.40
    ("\"
    0.40
    埠
    0.40
    thisStudent
    0.40
    Act Density 0.001%

    No Known Activations