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

    Neuronpedia

    INDEX
    Explanations

    och

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Rows
    -0.06
    abo
    -0.06
    ahi
    -0.06
    Ru
    -0.06
     valleys
    -0.06
     Ste
    -0.06
    _EXTENSION
    -0.06
    Rp
    -0.06
    nz
    -0.06
    Ce
    -0.06
    POSITIVE LOGITS
     Alabama
    0.08
     flashback
    0.07
     универ
    0.07
     fight
    0.06
     penchant
    0.06
     fought
    0.06
    _decision
    0.06
    _ALPHA
    0.06
    	Class
    0.06
    /english
    0.06
    Act Density 0.001%

    No Known Activations