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

    Neuronpedia

    INDEX
    Explanations

    Legal statements and evidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wholes
    -0.07
     Template
    -0.06
    _offsets
    -0.06
    Fall
    -0.06
    holding
    -0.06
    ivirus
    -0.06
    interpreter
    -0.06
    quee
    -0.06
     oma
    -0.06
    Leaders
    -0.06
    POSITIVE LOGITS
    JKLMNOP
    0.07
     оди
    0.06
     aus
    0.06
     muže
    0.06
     đường
    0.06
     허
    0.06
    (ti
    0.06
     enc
    0.06
    (loc
    0.06
     appart
    0.06
    Act Density 0.001%

    No Known Activations